Nemotron Embed VL 1B v2 API

Nemotron Embed VL 1B v2 is an embedding model by NVIDIA, available on the Venice API as text-embedding-nemotron-embed-vl-1b-v2. It runs privately, with zero data retention.

Nemotron Embed VL 1B v2 API pricing

Model ID	Variant	Privacy	Price
`text-embedding-nemotron-embed-vl-1b-v2`	Standard	Private	$0.01 per 1M tokens

Nemotron Embed VL 1B v2 specifications

Spec	Value
Provider	NVIDIA
Released	Apr 17, 2026
Privacy	Private
Open weights	Yes
Dimensions	2,048
Max input	32K tokens

How to use the Nemotron Embed VL 1B v2 API

Send requests to POST https://api.venice.ai/api/v1/embeddings with "model": "text-embedding-nemotron-embed-vl-1b-v2" and your API key.

curl https://api.venice.ai/api/v1/embeddings \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-embedding-nemotron-embed-vl-1b-v2",
    "input": "Private AI for everyone."
  }'

Nemotron Embed VL 1B v2 API FAQ

How much does the Nemotron Embed VL 1B v2 API cost?

$0.013 per 1M input tokens. Prices are in USD and can be paid in DIEM at parity.

What is the Nemotron Embed VL 1B v2 model ID?

Use text-embedding-nemotron-embed-vl-1b-v2 as the model parameter.

Is the Nemotron Embed VL 1B v2 API private?

Nemotron Embed VL 1B v2 is private: requests run on infrastructure Venice controls with zero data retention, and prompts and outputs are never stored or used for training.

How many dimensions do Nemotron Embed VL 1B v2 embeddings have?

2,048 dimensions, with up to 32K input tokens per item.

Which endpoint does the Nemotron Embed VL 1B v2 API use?

Call POST /embeddings.

Related models

BGE-EN-ICL API: $0.01 per 1M tokens
Multilingual E5 Large Instruct API: $0.01 per 1M tokens
Qwen3 Embedding 0.6B API: $0.01 per 1M tokens
Qwen3 Embedding 8B API: $0.01 per 1M tokens

Explore

By modality